# count items on columndomains_list = df['domains'].value_counts()# return first n rows in descending ordertop_domains = domains_list.nlargest(20)top_domains
Lista del top 20 de hashtags más usados y su frecuencia
Code
# convert dataframe column to listhashtags = df['hashtags'].to_list()# remove nan items from listhashtags = [x for x in hashtags ifnot pd.isna(x)]# split items into a list based on a delimiterhashtags = [x.split('|') for x in hashtags]# flatten list of listshashtags = [item for sublist in hashtags for item in sublist]# count items on listhashtags_count = pd.Series(hashtags).value_counts()# return first n rows in descending ordertop_hashtags = hashtags_count.nlargest(20)top_hashtags
# filter column from dataframeusers = df['mentioned_names'].to_list()# remove nan items from listusers = [x for x in users ifnot pd.isna(x)]# split items into a list based on a delimiterusers = [x.split('|') for x in users]# flatten list of listsusers = [item for sublist in users for item in sublist]# count items on listusers_count = pd.Series(users).value_counts()# return first n rows in descending ordertop_users = users_count.nlargest(20)top_users
# plot the data using plotlyfig = px.line(df, x='date', y='like_count', title='Likes over Time', template='plotly_white', hover_data=['text'])# show the plotfig.show()
Tokens
Lista del top 20 de los tokens más comunes y su frecuencia
Code
# load the spacy model for Spanishnlp = spacy.load("es_core_news_sm")# load stop words for SpanishSTOP_WORDS = nlp.Defaults.stop_words# Function to filter stop wordsdef filter_stopwords(text):# lower text doc = nlp(text.lower())# filter tokens tokens = [token.text for token in doc ifnot token.is_stop and token.text notin STOP_WORDS and token.is_alpha]return' '.join(tokens)# apply function to dataframe columndf['text_pre'] = df['text'].apply(filter_stopwords)# count items on columntoken_counts = df["text_pre"].str.split(expand=True).stack().value_counts()[:20]token_counts
Lista de las 10 horas con más cantidad de tweets publicados
Code
# extract hour from datetime columndf['hour'] = df['date'].dt.strftime('%H')# count items on columnhours_count = df['hour'].value_counts()# return first n rows in descending ordertop_hours = hours_count.nlargest(10)top_hours
Plataformas desde las que se publicaron contenidos y su frecuencia
Code
df['source_name'].value_counts()
source_name
Facebook 4460
Twitter Web App 2791
Hootsuite 2423
Instagram 1614
Twitter Web Client 1341
Postcron App 971
Twitter for iPad 868
Twitter for Android 682
Twitter for iPhone 627
TweetDeck 290
SocialGest 285
Google 254
Twitter Media Studio 230
Repost.social 167
Hootsuite Inc. 165
a Ning Network 106
Restream.io 72
Periscope 57
erased9_3Ud7cuBk0y 39
erased132190 3
Ustream.TV 2
LinkedIn 1
Twitter for Advertisers. 1
erased138961 1
Name: count, dtype: int64
Tópicos
Técnica de modelado de tópicos con transformers y TF-IDF
Code
# visualize topicstopic_model.visualize_topics()
Reducción de tópicos
Mapa con 10 tópicos del contenido de los tweets
Code
# visualize topicstopic_model.visualize_topics()
Términos por tópico
Code
topic_model.visualize_barchart(top_n_topics=11)
Análisis de tópicos
Selección de tópicos que tocan temas de género
Code
# selection of topicstopics = [1]keywords_list = []for topic_ in topics: topic = topic_model.get_topic(topic_) keywords = [x[0] for x in topic] keywords_list.append(keywords)# flatten list of listsword_list = [item for sublist in keywords_list for item in sublist]# use apply method with lambda function to filter rowsfiltered_df = df[df['text_pre'].apply(lambda x: any(word in x for word in word_list))]percentage =round(100*len(filtered_df) /len(df), 2)print(f"Del total de {len(df)} tweets de @misionpaz_, alrededor de {len(filtered_df)} hablan sobre temas de género, es decir, cerca del {percentage}%")
Del total de 17450 tweets de @misionpaz_, alrededor de 2129 hablan sobre temas de género, es decir, cerca del 12.2%
Code
# drop rows with 0 values in two columnsfiltered_df = filtered_df[(filtered_df.like_count !=0) & (filtered_df.retweet_count !=0)]# add a new column with the sum of two columnsfiltered_df['impressions'] = (filtered_df['like_count'] + filtered_df['retweet_count'])/2# extract year from datetime columnfiltered_df['year'] = filtered_df['date'].dt.year# remove urls, mentions, hashtags and numbersp.set_options(p.OPT.URL)filtered_df['tweet_text'] = filtered_df['text'].apply(lambda x: p.clean(x))# Create scatter plotfig = px.scatter(filtered_df, x='like_count', y='retweet_count', size='impressions', color='year', hover_name='tweet_text')# Update title and axis labelsfig.update_layout( title='Tweets talking about gender with most Likes and Retweets', xaxis_title='Number of Likes', yaxis_title='Number of Retweets')fig.show()